AI Quick Reference
Practical references for vector data lakes, Milvus components, retrieval indexes, AI agents, data curation, and production systems. Browse questions by topic.
- How does the Milvus architecture separate ingestion, storage, and search?
- What is Knowhere, and how does Milvus use it?
- How can Attu help you inspect and manage Milvus?
- What does the milvus-storage project provide?
- How do you locate a bottleneck across Milvus components?
- How should you build a reproducible application workflow with PyMilvus?
- How does the Spark-Milvus connector fit into an AI data pipeline?
- When should you use DISKANN in Milvus?
- What is GPU_CAGRA, and when does it help vector search?
- How do HNSW_SQ, HNSW_PQ, and HNSW_PRQ change the trade-offs?
- What is IVF_RABITQ, and how should you evaluate it?
- How does a sparse inverted index differ from dense ANN?
- How does MINHASH_LSH help find near-duplicate text?
- Why use a FLAT baseline when tuning an ANN index?
- When should you use range search instead of only top-k?
- What is late-interaction retrieval, and how can embedding lists help?
- How does mmap differ from a disk-oriented ANN index?
- What is agentic search, and where does a vector database fit?
- How should an agent choose between vector, keyword, and structured search?
- How do working, episodic, semantic, and procedural agent memory differ?
- How should an agent memory system handle corrections, expiry, and deletion?
- How can vector search retrieve useful agent trajectories?
- How should you select rollouts for an offline agent-training dataset?
- When is a semantic cache useful, and how do you prevent stale answers?